111 citations · 175 across the 26 of their papers we have counts for
27 papers
Cross-Modal Knowledge Distillation for Speech Large Language Models
Enzhi Wang, Qicheng Li, Zhiyuan Tang +1
In this work, we present the first systematic evaluation of catastrophic forgetting and modality inequivalence in speech large language models, showing that introducing speech capa…
Chain of Correction for Full-text Speech Recognition with Large Language Models
Zhiyuan Tang, Dong Wang, Zhikai Zhou +3
Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) is attracting increased attention for its ability to address a wide range of err…
Full-text Error Correction for Chinese Speech Recognition with Large Language Model
Zhiyuan Tang, Dong Wang, Shen Huang +1
Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from s…
Semantic Data Augmentation for End-to-End Mandarin Speech Recognition
Jianwei Sun, Zhiyuan Tang, Hengxin Yin +6
End-to-end models have gradually become the preferred option for automatic speech recognition (ASR) applications. During the training of end-to-end ASR, data augmentation is a quit…
Can We Trust Deep Speech Prior?
Ying Shi, Haolin Chen, Zhiyuan Tang +3
Recently, speech enhancement (SE) based on deep speech prior has attracted much attention, such as the variational auto-encoder with non-negative matrix factorization (VAE-NMF) arc…
AP20-OLR Challenge: Three Tasks and Their Baselines
Zheng Li, Miao Zhao, Qingyang Hong +5
This paper introduces the fifth oriental language recognition (OLR) challenge AP20-OLR, which intends to improve the performance of language recognition systems, along with APSIPA…
ASR-Free Pronunciation Assessment
Sitong Cheng, Zhixin Liu, Lantian Li +3
Most of the pronunciation assessment methods are based on local features derived from automatic speech recognition (ASR), e.g., the Goodness of Pronunciation (GOP) score. In this p…
AP19-OLR Challenge: Three Tasks and Their Baselines
Zhiyuan Tang, Dong Wang, Liming Song
This paper introduces the fourth oriental language recognition (OLR) challenge AP19-OLR, including the data profile, the tasks and the evaluation principles. The OLR challenge has…
Phonetic-attention scoring for deep speaker features in speaker verification
Lantian Li, Zhiyuan Tang, Ying Shi +1
Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech s…
Gaussian-Constrained training for speaker verification
Lantian Li, Zhiyuan Tang, Ying Shi +1
Neural models, in particular the d-vector and x-vector architectures, have produced state-of-the-art performance on many speaker verification tasks. However, two potential problems…
AP18-OLR Challenge: Three Tasks and Their Baselines
Zhiyuan Tang, Dong Wang, Qing Chen
The third oriental language recognition (OLR) challenge AP18-OLR is introduced in this paper, including the data profile, the tasks and the evaluation principles. Following the eve…
Deep factorization for speech signal
Lantian Li, Dong Wang, Yixiang Chen +3
Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individu…
Human and Machine Speaker Recognition Based on Short Trivial Events
Miao Zhang, Xiaofei Kang, Yanqing Wang +4
Trivial events are ubiquitous in human to human conversations, e.g., cough, laugh and sniff. Compared to regular speech, these trivial events are usually short and unclear, thus ge…
Full-info Training for Deep Speaker Feature Learning
Lantian Li, Zhiyuan Tang, Dong Wang +1
In recent studies, it has shown that speaker patterns can be learned from very short speech segments (e.g., 0.3 seconds) by a carefully designed convolutional & time-delay deep neu…
AP17-OLR Challenge: Data, Plan, and Baseline
Zhiyuan Tang, Dong Wang, Yixiang Chen +1
We present the data profile and the evaluation plan of the second oriental language recognition (OLR) challenge AP17-OLR. Compared to the event last year (AP16-OLR), the new challe…
Deep Factorization for Speech Signal
Dong Wang, Lantian Li, Ying Shi +2
Speech signals are complex intermingling of various informative factors, and this information blending makes decoding any of the individual factors extremely difficult. A natural i…
Deep Speaker Verification: Do We Need End to End?
Dong Wang, Lantian Li, Zhiyuan Tang +1
End-to-end learning treats the entire system as a whole adaptable black box, which, if sufficient data are available, may learn a system that works very well for the target task. T…
Phone-aware Neural Language Identification
Zhiyuan Tang, Dong Wang, Yixiang Chen +2
Pure acoustic neural models, particularly the LSTM-RNN model, have shown great potential in language identification (LID). However, the phonetic information has been largely overlo…
Deep Speaker Feature Learning for Text-independent Speaker Verification
Lantian Li, Yixiang Chen, Ying Shi +2
Recently deep neural networks (DNNs) have been used to learn speaker features. However, the quality of the learned features is not sufficiently good, so a complex back-end model, e…
Phonetic Temporal Neural Model for Language Identification
Zhiyuan Tang, Dong Wang, Yixiang Chen +2
Deep neural models, particularly the LSTM-RNN model, have shown great potential for language identification (LID). However, the use of phonetic information has been largely overloo…
OC16-CE80: A Chinese-English Mixlingual Database and A Speech Recognition Baseline
Dong Wang, Zhiyuan Tang, Difei Tang +1
We present the OC16-CE80 Chinese-English mixlingual speech database which was released as a main resource for training, development and test for the Chinese-English mixlingual spee…
Multi-task Recurrent Model for True Multilingual Speech Recognition
Zhiyuan Tang, Lantian Li, Dong Wang
Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a fe…
Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition
Zhiyuan Tang, Ying Shi, Dong Wang +2
Recurrent neural networks (RNNs) have shown clear superiority in sequence modeling, particularly the ones with gated units, such as long short-term memory (LSTM) and gated recurren…
Collaborative Learning for Language and Speaker Recognition
Lantian Li, Zhiyuan Tang, Dong Wang +3
This paper presents a unified model to perform language and speaker recognition simultaneously and altogether. The model is based on a multi-task recurrent neural network where the…